Triple

T12122677
Position Surface form Disambiguated ID Type / Status
Subject Banyuls-sur-Mer E288731 entity
Predicate locatedNorthOf P305 FINISHED
Object Cerbère E485813 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Cerbère | Statement: [Banyuls-sur-Mer, locatedNorthOf, Cerbère]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cerbère
Context triple: [Banyuls-sur-Mer, locatedNorthOf, Cerbère]
  • A. Cerbère chosen
    Cerbère is a coastal commune in southern France near the Spanish border, known for its Mediterranean scenery and winegrowing tradition.
  • B. Cerberus
    Cerberus is the multi-headed hound from Greek mythology that guards the entrance to the underworld, preventing the dead from leaving.
  • C. Remus
    Remus is a male given name best known from the Harry Potter character Remus Lupin and the mythological twin of Romulus in Roman legend.
  • D. Karneios
    Karneios is an ancient Greek month, particularly in the Spartan calendar, associated with the festival of Karneia in honor of Apollo Karneios.
  • E. Vulpius
    Vulpius is a German surname most notably associated with Christiane Vulpius, the longtime companion and later wife of writer Johann Wolfgang von Goethe.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d6ab4b5e4c81909950b17151eb0951 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d91578fd88819099adf55c93d549fc completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f686d6c08190b1f1ca2d5a51f5df completed May 2, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:49 p.m.